Functional Diversity Evaluation on Functional Diversity Taxonomy Study Category E
1Spearman CorrelationGemini-2.5-Flash
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Gemini-2.5-FlashTaxonomy-guided=true2025.09 | 1 | — | |
| GPT-4oTaxonomy-guided=true2025.09 | 0.83 | — | |
| Claude-4-SonnetTaxonomy-guided=true2025.09 | 0.83 | — | |
| Novelty-Bench Functional Diversity2025.09 | 0.69 | — | |
| Embedding Diversity2025.09 | 0.66 | — | |
| Compression Diversity2025.09 | 0.62 | — | |
| Vocabulary Diversity2025.09 | 0.46 | — | |
| Human Inter-Rater Agreement2025.09 | — | 92 |